Plan

Turns abstract feature requests into verified task lists that actually survive implementation. Built from 200+ real planning sessions, it enforces one simple rule: every task needs a concrete verification method, whether that's a passing test, a typecheck, or a curl command. The phases walk you through scoping (skip planning for tiny changes), exploration (read the actual code), decomposition (2-5 minute tasks with explicit dependencies), and tracking in Sibyl so plans outlive your context window. The parallelization markers are clever for orchestration handoff. Honest about replanning being normal, not failure. If you've ever written a plan that collapsed the moment you touched code, this codifies what makes the difference.

skills.sh installs: 605
GitHub stars: 36
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add hyperb1iss/hyperskills --skill plan --agent claude-code

Installs into .claude/skills of the current project.

Files

Structured Planning

The user's instructions take precedence over this skill; carry existing authorization forward and do not add approval gates. If the user requested only a plan, deliver the plan without starting implementation.

Size the Plan by Uncertainty

Work shape	Planning depth
Clear, reversible change with a direct check	Execute with a brief inline plan
Several dependent behaviors with known patterns	Record tasks, interfaces, and acceptance checks
Uncertain architecture or migration	Resolve decisive unknowns and plan a representative vertical slice
Work spanning agents, sessions, or environments	Preserve ownership, state, dependencies, and resumption steps

File count is a poor proxy for risk: a one-line authorization change can need more analysis than a mechanical rename across many files.